Mastery: your playbook

Your mastery artifact is a research trail with question, query log, inclusion rules, source cards, claim-evidence matrix, and citation audit. It should let a competent colleague repeat investigate how later school start times affect teenagers without inventing evidence without inheriting unstated assumptions. Include the job card, source requirements, prompt contract, examples, rubric, privacy boundary, escalation rule, and recovery steps.

Use scope → search → inspect → extract → synthesize → cite as the spine. For every stage, name the input, action, output, owner, check, and stop condition. Include the concrete prompt:

Topic: effects of later secondary-school start times on adolescent sleep and attendance. Propose one focused question, five search phrases including a skeptical angle, and inclusion/exclusion rules. Do not provide citations. Mark every factual statement that will require a source.

Then include a specimen response: A question bounded by population, intervention, outcomes, and time; search phrases include counterevidence and implementation costs; no fabricated bibliography appears. Label it as an example, not a guaranteed result. Attach proof from the independent check: you must open every source, check author/date/method, follow quotes to the original, compare primary findings with limitations, and label unsupported claims.

Run the same playbook on a second case that differs in one meaningful way. Keep the quality bar fixed. Explain which context fields and constraints changed. If the workflow only succeeds on the memorized example, it is not mastered.

Teach the method in five minutes to someone who has not read this chapter. Ask them to identify the source of truth, the riskiest failure, and the human decision. Their answers reveal whether your playbook is explicit.

Score yourself:

1. Framing: I can reject work outside the stated job.
2. Context: I distinguish evidence, assumptions, and untrusted input.
3. Prompting: I constrain output and request inspectable artifacts.
4. Verification: I use an external check, not model confidence.
5. Safety: I enforce this boundary: share only excerpts you are permitted to process; remove participant identifiers, unpublished interview material, paywalled full text, and confidential research data.
6. Operations: I can recover from invented citations; treating search snippets as evidence; collapsing correlation into causation; hiding disagreement; quoting a summary instead of the source.
7. Communication: I disclose limitations and ownership clearly.

A weak score is a practice target, not a reason to pad the playbook. AI can map a search and organize supplied evidence; it is not the evidence. The non-negotiable habit is opening and judging the original source.

Package the project as produce a three-source evidence table and a two-page synthesis that preserves uncertainty and study limitations. Show the before state, constraint decisions, failed case, correction, measured result, and reflection. Remove sensitive inputs and avoid claiming impact you did not measure. Professional credibility comes from showing judgment under constraints.

Apply the playbook to a claim that phone bans improve classroom attention. Define the age group, setting, outcome, and publication window before searching. Include one skeptical query and separate policy reports from empirical studies. Open every candidate source, record design and sample, and exclude any citation you cannot retrieve. Give the model only labeled excerpts and require “not supported” when evidence is absent. In the synthesis, distinguish measured attention from grades or teacher impressions. End with one conclusion the evidence supports, one it does not support, and one new source needed to reduce uncertainty.